INDEX

Explanations

geographical locations and landmarks

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Shale

-0.58

 Shropshire

-0.52

!("{}",

-0.50

 Borough

-0.49

Havolalar

-0.48

 Barbados

-0.47

Rihanna

-0.46

 Maori

-0.46

taciones

-0.46

 strconv

-0.45

POSITIVE LOGITS

 Vietnamese

1.35

 Vietnam

1.35

 Saigon

1.30

 Hanoi

1.23

 Viet

1.21

 Nguyen

1.19

Vietnam

1.19

Vietnamese

1.10

Viet

1.07

 VIET

1.05

Activations Density 0.169%

geographical locations and landmarks

No Comments

No Known Activations